Statistical Analysis and Modeling in R: Performing Clustering

IN THIS COURSE

• 1.  Course Overview
  2m 10s
  In this video, you’ll learn more about your instructor and this course. In this course, you’ll learn the differences between supervised and unsupervised learning and see how regression and classification algorithms differ from clustering in how they learn patterns from data. You’ll discover the basic principles of clustering models and get an overview of how K means clustering works to find logical groupings in your data. You’ll also learn evaluation techniques used in clustering. FREE ACCESS
• 2.  Recognizing and Evaluating Clustering Models
  11m 55s
  In this video, you’ll learn more about Clustering. Clustering is a machine learning technique used to find patterns or logical groupings in data. Clustering as a machine learning technique is fundamentally different from regression and classification algorithms. Both regression and classifications are supervised machine learning techniques. Supervised learning techniques require training data, which are classified or labeled to learn from that data. Supervised algorithms use training data that have labeled values. FREE ACCESS
• 3.  Investigating and Visualizing Clustering Data in R
  3m 46s
  In this video, you’ll watch a demo. In this demo, you'll see how to perform k-means clustering on data that has just two variables that can be expressed on the two axes of a coordinate plane. First, you’ll invoke rm list = ls to clear your R programming memory to start afresh. Before you perform cluster analysis on your data, you'll visualize and understand your data. You’ll use ggplot2. FREE ACCESS
• 4.  Performing K-means Clustering, Interpreting Results
  10m 25s
  In this video, you’ll watch a demo. In this demo, you'll run your k-means Clustering algorithm. You’ll notice the k-means algorithm requires you to specify the number of clusters you want to find upfront. You’ll invoke the k-means function, pass in the data you want to perform clustering on, and that’s the income.score.data, iter.max is set to 10. This means you’ll want the k-means algorithm to run for 10 iterations. FREE ACCESS
• 5.  Using R to Find the Optimal Number of Clusters
  10m 56s
  In this video, you’ll watch a demo. In this demo, you'll see how to use the elbow method to determine the right number of clusters for your data. You'll be using functions from the tidyverse collection of data science packages. First, you’ll install the tidyverse package within your current R programming environment. Once the package has been installed, you’ll include the tidyverse as a part of your current program using the library function. FREE ACCESS
• 6.  Using K-means Clustering on Multi-attribute Data
  8m 23s
  In this video, you’ll watch a demo. In this demo, you'll learn how to apply the k-means clustering algorithm on data with multiple variables. You’ll learn how to find and visualize clusters in such data. You’ll start by invoking the rm function passing in list = ls to remove objects from R's memory. Then you’ll include a number of packages in your current program using the library function, ggplot2, factoextra, and the cluster packages. FREE ACCESS
• 7.  Course Summary
  2m 9s
  In this video, you’ll summarize what you’ve learned in this course. You learned to apply an unsupervised learning technique to find logical patterns in unlabeled data. You learned the difference between supervised and unsupervised learning. You also saw that regression and classification models were both examples of supervised learning and used labeled training data to improve your model. You learned Clustering is an unsupervised learning technique that self discovers patterns in data. FREE ACCESS